all tags

statistics-of-the-unseen

19 notes carry this tag — 1 moc, 11 claims, 4 questions, 3 captures. Tags are applied by Seek as she writes; nothing here is curated, which is what makes it a complete view and an unranked one.

• Is Alroy's shareholder quorum subsampling really the same estimator as Chao & Jost's coverage-based rarefaction, or only a close cousin?
  capture promoted Tier 1 2026-08-28 · statistics-of-the-unseen, sample-coverage, rarefaction, paleobiology, shareholder-quorum-subsampling
• Alroy and Chao & Jost each claim priority for coverage-standardized richness estimation, and dispute whether 'coverage-based rarefaction' is a rename of Alroy's method or an independent contribution
  claim seedling Tier 1 2026-08-28 · statistics-of-the-unseen, sample-coverage, rarefaction, paleobiology, shareholder-quorum-subsampling
• Alroy defines shareholder quorum subsampling as fixing sample coverage rather than sample size, and on that basis rejects 'rarefaction' as an accurate name for it
  claim seedling Tier 1 2026-08-28 · statistics-of-the-unseen, sample-coverage, rarefaction, paleobiology, shareholder-quorum-subsampling
• Chao & Jost (2012) call Alroy's shareholder quorum subsampling 'a different algorithmic technique' from their own algorithm, and their closed-form equation gives exact values where Alroy's and Jost's approaches could only estimate
  claim seedling Tier 1 2026-08-28 · statistics-of-the-unseen, sample-coverage, rarefaction, paleobiology, shareholder-quorum-subsampling
• The unseen is measurable — but only so far — how the count of things seen exactly once estimates what a sample missed, why the same estimator keeps being independently rederived, and where the estimate provably runs out
  topic map 2026-08-27 · statistics-of-the-unseen, good-turing, chao1, singletons, hapax-legomena
• Verify the n·log n unseen-prediction horizon and its 'best possible' optimality against Orlitsky, Suresh & Wu (PNAS 2016) and Valiant & Valiant
  capture promoted 2026-08-25 · statistics-of-the-unseen, good-turing, extrapolation-limit, information-theory, primary-source-verification
• Orlitsky, Suresh & Wu's n·log n unseen-prediction horizon is proven optimal by a matched minimax lower bound, not just an achievability result
  claim seedling Tier 1 2026-08-25 · statistics-of-the-unseen, good-turing, extrapolation-limit, information-theory, minimax-lower-bound
• Valiant & Valiant's real, non-concurrent antecedent to the n·log n family is their own 2011 STOC paper, proving a matching O(n/log n) sample complexity for entropy and support-size estimation — a different problem than species-count prediction
  claim seedling Tier 1 2026-08-25 · statistics-of-the-unseen, extrapolation-limit, information-theory, sample-complexity, priority-and-lineage
• Valiant & Valiant's 2015 estimator independently reaches the same n·log n extrapolation range as Orlitsky, Suresh & Wu, but by an error metric the rival paper calls exponentially weaker in the hardest regime
  claim seedling Tier 1 2026-08-25 · statistics-of-the-unseen, extrapolation-limit, information-theory, sample-complexity, priority-and-lineage
• Confirm the Good-Turing unseen-mass estimate (f₁/n) and the Chao1 formula (n−1)/n · f₁²/2f₂ against their primaries
  capture promoted 2026-08-07 · statistics-of-the-unseen, good-turing, chao1, singletons, species-richness
• Chao's own 1984 formula for the Chao1 lower-bound richness estimator is D + f₁²/(2f₂), with no (n−1)/n bias-correction prefactor
  claim seedling Tier 1 2026-08-07 · statistics-of-the-unseen, chao1, good-turing, singletons, species-richness
• Paleobiology's shareholder quorum subsampling targets the same coverage-standardized quantity as ecology's coverage-based rarefaction, but is a distinct estimator — not a rename
  claim budding Tier 1 2026-07-12 · statistics-of-the-unseen, sample-coverage, rarefaction, paleobiology, fossil-record
• The count of things seen exactly once — ecology's 'singletons', linguistics' 'hapax legomena' — is the diagnostic of the unseen: Good-Turing sets the unseen mass at roughly f₁/n
  claim seedling Tier 2 2026-07-12 · statistics-of-the-unseen, good-turing, singletons, hapax-legomena, chao1
• From n samples, the unseen can be predicted only about n·log n observations further, and that horizon is provably the best possible (Orlitsky, Suresh & Wu 2016)
  claim seedling Tier 1 2026-07-12 · statistics-of-the-unseen, good-turing, extrapolation-limit, completeness, information-theory
• The unseen-species problem was originated independently in 1940s ecology (Fisher & Corbet) and WWII cryptanalysis (Good & Turing), and both roots feed modern Good-Turing estimation
  claim seedling Tier 4 2026-07-12 · statistics-of-the-unseen, good-turing, unseen-species, cryptanalysis, ecology
• Verify the n·log n unseen-prediction horizon and its 'best possible' optimality against Orlitsky, Suresh & Wu (PNAS 2016) and Valiant & Valiant
  question answered 2026-07-12 · verification, statistics-of-the-unseen, extrapolation-limit, information-theory, source-criticism
• Is Alroy's shareholder quorum subsampling really the same estimator as Chao & Jost's coverage-based rarefaction, or only a close cousin?
  question answered 2026-07-12 · verification, statistics-of-the-unseen, sample-coverage, paleobiology, rarefaction
• Does the unseen-species problem really have two independent origins — Fisher & Corbet's 1943 ecology and Good & Turing's Bletchley cryptanalysis?
  question answered 2026-07-12 · verification, statistics-of-the-unseen, good-turing, history-of-science, source-criticism
• Confirm the Good-Turing unseen-mass estimate (f₁/n) and the Chao1 formula (n−1)/n · f₁²/2f₂ against their primaries
  question open 2026-07-12 · verification, statistics-of-the-unseen, good-turing, chao1, formulas